Gemini API pricing & models
KumoAPI serves 3 Google models: Gemini 3.5 Flash-Lite, Gemini 3.7 Flash, Gemini 3.1 Pro (Preview). Input costs 0.3–2 Credits / M tokens (1 Credit = ¥1). Compatible with Gemini generateContent; one API key for all of them, pay as you go.
Google model pricing
KumoAPI default channel price in Credits (1 Credit = ¥1); struck-through is the list price. Click a model for full pricing, protocols and uptime.
| Model | Context · output | Input / M | Output / M | 7-day uptime |
|---|---|---|---|---|
| Gemini 3.5 Flash-Litegemini-3.5-flash-lite | 1M · 64K | 0.3 | 2.5 | — |
| Gemini 3.7 Flashgemini-3.7-flash | 1M · 64K | 0.75 | 3.75 | — |
| Gemini 3.1 Pro (Preview)gemini-3.1-pro-preview | 1M · 64K | 2 | 12 | — |
Input (prompt) / Output (completion) are per 1M tokens; image and video models show their primary unit price. Uptime comes from KumoAPI probes; a dash means not probed yet.
How to call Google models
Samples use Gemini 3.5 Flash-Lite; change the model field to call any other model from this vendor.
Google GenAI SDK or any generateContent client: point the base URL at https://api.kumoapi.com.
curl "https://api.kumoapi.com/v1beta/models/gemini-3.5-flash-lite:generateContent" \
-H "x-goog-api-key: $SOLEAPI_KEY" \
-H "content-type: application/json" \
-d '{
"contents": [{"parts": [{"text": "Explain prompt caching in one sentence"}]}]
}'Google model capabilities
Exactly as flagged in the catalog.
| Capability | Gemini 3.5 Flash-Lite | Gemini 3.7 Flash | Gemini 3.1 Pro (Preview) |
|---|---|---|---|
| Vision | |||
| Function Calling | |||
| Reasoning | |||
| Prompt Caching | |||
| Response Schema | |||
| Audio | |||
| Video | |||
| File Input | |||
| Streaming | |||
| Web Search | |||
| Realtime | |||
| Session | |||
| Media | |||
| Multipart Form | |||
| Binary Response |
Compare Google models
Pricing, context, capabilities and uptime side by side.
FAQ
How much does the Gemini API cost on KumoAPI?
Google models cost 0.3–2 Credits / M input tokens, with 1 Credit = ¥1; the cheapest is Gemini 3.5 Flash-Lite. That is up to 0% below list price — see the table above.
How do I call Gemini models on KumoAPI with the official SDK?
Point the base URL at https://api.kumoapi.com and use a KumoAPI key. Gemini generateContent are supported and request bodies are identical to the official API.
Which Gemini model has the largest context window?
Gemini 3.5 Flash-Lite, with 1M tokens. Context and max output for every model are in the pricing table above.
Can I pay for the Gemini API with Alipay?
Yes. KumoAPI accepts Alipay top-ups; 1 Credit = ¥1, billed per use with no monthly fee or minimum.
One API key for every Google model
Free credits on sign-up, pay as you go, no monthly fee.